bio 0.7.0

data/lib/bio/db/kegg/genes.rb

@@ -0,0 +1,293 @@
+#
+# bio/db/kegg/genes.rb - KEGG/GENES database class
+#
+#   Copyright (C) 2001, 2002 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#  $Id: genes.rb,v 0.22 2005/11/09 12:30:07 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+
+  class KEGG
+
+    class GENES < KEGGDB
+
+      DELIMITER	= RS = "\n///\n"
+      TAGSIZE	= 12
+
+      def initialize(entry)
+        super(entry, TAGSIZE)
+      end
+
+
+      def entry
+        unless @data['ENTRY']
+          hash = Hash.new('')
+          if get('ENTRY').length > 30
+            e = get('ENTRY')
+            hash['id']       = e[12..29].strip
+            hash['division'] = e[30..39].strip
+            hash['organism'] = e[40..80].strip
+          end
+          @data['ENTRY'] = hash
+        end
+        @data['ENTRY']
+      end
+
+      def entry_id
+        entry['id']
+      end
+
+      def division
+        entry['division']			# CDS, tRNA etc.
+      end
+
+      def organism
+        entry['organism']			# H.sapiens etc.
+      end
+
+      def name
+        field_fetch('NAME')
+      end
+
+      def genes
+        name.split(', ')
+      end
+
+      def gene
+        genes.first
+      end
+
+      def definition
+        field_fetch('DEFINITION')
+      end
+
+      def eclinks
+#       definition.slice(/\[EC:(.*?)\]/, 1)	# ruby >= 1.7
+#       definition.scan(/\[EC:(.*?)\]/).flatten
+        if /\[EC:(.*?)\]/.match(definition)
+          $1.split(/\s+/)
+        else
+          []
+        end
+      end
+
+      def splinks
+#       definition.slice(/\[SP:(.*?)\]/, 1)	# ruby >= 1.7
+#       definition.scan(/\[SP:(.*?)\]/).flatten
+        if /\[SP:(.*?)\]/.match(definition)
+          $1.split(/\s+/)
+        else
+          []
+        end
+      end
+
+      def keggclass
+        field_fetch('CLASS')
+      end
+
+      def pathways
+        keggclass.scan(/\[PATH:(.*?)\]/).flatten
+      end
+
+      def position
+        unless @data['POSITION']
+          @data['POSITION'] = fetch('POSITION').gsub(/\s/, '')
+        end
+        @data['POSITION']
+      end
+
+      def gbposition
+        position.sub(/.*?:/, '')
+      end
+
+      def chromosome
+        if position =~ /:/
+          position.sub(/:.*/, '')
+        else
+          nil
+        end
+      end
+
+      def dblinks
+        unless @data['DBLINKS']
+          hash = {}
+          get('DBLINKS').scan(/(\S+):\s*(.*)\n?/).each do |db, str|
+            id_array = str.strip.split(/\s+/)
+            hash[db] = id_array
+          end
+          @data['DBLINKS'] = hash
+        end
+        @data['DBLINKS']		# Hash of Array of DB IDs in DBLINKS
+      end
+
+      def codon_usage(codon = nil)
+        unless @data['CODON_USAGE']
+          ary = []
+          get('CODON_USAGE').sub(/.*/,'').each_line do |line|	# cut 1st line
+            line.chomp.sub(/^.{11}/, '').scan(/..../) do |cu|
+              ary.push(cu.to_i)
+            end
+          end
+          @data['CODON_USAGE'] = ary
+        end
+
+        if codon
+          h = { 't' => 0, 'c' => 1, 'a' => 2, 'g' => 3 }
+          x, y, z = codon.downcase.scan(/\w/)
+          codon_num = h[x] * 16 + h[y] * 4 + h[z]
+          @data['CODON_USAGE'][codon_num]	# CODON_USAGE of the codon
+        else
+          return @data['CODON_USAGE']	# Array of CODON_USAGE (default)
+        end
+      end
+
+      def cu
+        hash = Hash.new
+        list = codon_usage
+        base = %w(t c a g)
+        base.each_with_index do |x, i|
+          base.each_with_index do |y, j|
+            base.each_with_index do |z, k|
+              hash["#{x}#{y}#{z}"] = list[i*16 + j*4 + k]
+            end
+          end
+        end
+        return hash
+      end
+
+      def aaseq
+        unless @data['AASEQ']
+          @data['AASEQ'] = Sequence::AA.new(fetch('AASEQ').gsub(/[\s\d\/]+/, ''))
+        end
+        @data['AASEQ']
+      end
+
+      def aalen
+        @data['AALEN'] = aaseq.length
+      end
+
+      def ntseq
+        unless @data['NTSEQ']
+          @data['NTSEQ'] = Sequence::NA.new(fetch('NTSEQ').gsub(/[\s\d\/]+/, ''))
+        end
+        @data['NTSEQ']
+      end
+      alias naseq ntseq
+
+      def ntlen
+        @data['NTLEN'] = ntseq.length
+      end
+      alias nalen ntlen
+
+    end
+
+  end
+
+end
+
+
+
+if __FILE__ == $0
+
+  require 'bio/io/fetch'
+
+  e = Bio::Fetch.query('genes', 'b0002')
+  g = Bio::KEGG::GENES.new(e)
+
+  p g.entry
+  p g.entry_id
+  p g.division
+  p g.name
+  p g.gene
+  p g.definition
+  p g.keggclass
+  p g.position
+  p g.dblinks
+  p g.codon_usage
+  p g.cu
+  p g.aaseq
+  p g.aalen
+  p g.naseq
+  p g.nalen
+  p g.eclinks
+  p g.splinks
+  p g.pathways
+
+end
+
+
+=begin
+
+= Bio::KEGG::GENES
+
+=== Initialize
+
+--- Bio::KEGG::GENES.new
+
+=== ENTRY
+
+--- Bio::KEGG::GENES#entry -> Hash
+--- Bio::KEGG::GENES#entry_id -> String
+--- Bio::KEGG::GENES#division -> String
+--- Bio::KEGG::GENES#organism -> String
+
+=== NAME
+
+--- Bio::KEGG::GENES#name -> String
+--- Bio::KEGG::GENES#genes -> Array
+--- Bio::KEGG::GENES#gene -> String
+
+=== DEFINITION
+
+--- Bio::KEGG::GENES#definition -> String
+--- Bio::KEGG::GENES#eclinks -> Array
+--- Bio::KEGG::GENES#splinks -> Array
+
+=== CLASS
+
+--- Bio::KEGG::GENES#keggclass -> String
+--- Bio::KEGG::GENES#pathways -> Array
+
+=== POSITION
+
+--- Bio::KEGG::GENES#position -> String
+
+=== DBLINKS
+
+--- Bio::KEGG::GENES#dblinks -> Hash
+
+=== CODON_USAGE
+
+--- Bio::KEGG::GENES#codon_usage(codon = nil) -> Array or Fixnum
+--- Bio::KEGG::GENES#cu -> Hash
+
+=== AASEQ
+
+--- Bio::KEGG::GENES#aaseq -> Bio::Sequence::AA
+--- Bio::KEGG::GENES#aalen -> Fixnum
+
+=== NTSEQ
+
+--- Bio::KEGG::GENES#ntseq -> Bio::Sequence::NA
+--- Bio::KEGG::GENES#naseq -> Bio::Sequence::NA
+--- Bio::KEGG::GENES#ntlen -> Fixnum
+--- Bio::KEGG::GENES#nalen -> Fixnum
+
+=end

data/lib/bio/db/kegg/genome.rb

@@ -0,0 +1,362 @@
+#
+# bio/db/kegg/genome.rb - KEGG/GENOME database class
+#
+#   Copyright (C) 2001, 2002 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#  $Id: genome.rb,v 0.14 2005/09/08 01:22:11 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+
+  class KEGG
+
+    class GENOME < KEGGDB
+
+      DELIMITER	= RS = "\n///\n"
+      TAGSIZE	= 12
+
+      def initialize(entry)
+        super(entry, TAGSIZE)
+      end
+
+
+      # ENTRY
+      def entry_id
+        field_fetch('ENTRY')
+      end
+      
+      # NAME
+      def name
+        field_fetch('NAME')
+      end
+
+      # DEFINITION
+      def definition
+        field_fetch('DEFINITION')
+      end
+      alias organism definition
+
+      # TAXONOMY
+      def taxonomy
+        unless @data['TAXONOMY']
+          taxid, lineage = subtag2array(get('TAXONOMY'))
+          taxid   = taxid   ? truncate(tag_cut(taxid))   : ''
+          lineage = lineage ? truncate(tag_cut(lineage)) : ''
+          @data['TAXONOMY'] = {
+            'taxid'	=> taxid,
+            'lineage'	=> lineage,
+          }
+          @data['TAXONOMY'].default = ''
+        end
+        @data['TAXONOMY']
+      end
+
+      def taxid
+        taxonomy['taxid']
+      end
+
+      def lineage
+        taxonomy['lineage']
+      end
+
+      # COMMENT
+      def comment
+        field_fetch('COMMENT')
+      end
+      
+      # REFERENCE
+      def references
+        unless @data['REFERENCE']
+          ary = []
+          toptag2array(get('REFERENCE')).each do |ref|
+            hash = Hash.new('')
+            subtag2array(ref).each do |field|
+              case tag_get(field)
+              when /AUTHORS/
+                authors = truncate(tag_cut(field))
+                authors = authors.split(', ')
+                authors[-1] = authors[-1].split(/\s+and\s+/)
+                authors = authors.flatten.map { |a| a.sub(',', ', ') }
+                hash['authors']	= authors
+              when /TITLE/
+                hash['title']	= truncate(tag_cut(field))
+              when /JOURNAL/
+                journal = truncate(tag_cut(field))
+                if journal =~ /(.*) (\d+):(\d+)-(\d+) \((\d+)\) \[UI:(\d+)\]$/
+                  hash['journal']	= $1
+                  hash['volume']	= $2
+                  hash['pages']		= $3
+                  hash['year']		= $5
+                  hash['medline']	= $6
+                else
+                  hash['journal'] = journal
+                end
+              end
+            end
+            ary.push(Reference.new(hash))
+          end
+          @data['REFERENCE'] = References.new(ary)
+        end
+        @data['REFERENCE']
+      end
+
+      # CHROMOSOME
+      def chromosomes
+        unless @data['CHROMOSOME']
+          @data['CHROMOSOME'] = []
+          toptag2array(get('CHROMOSOME')).each do |chr|
+            hash = Hash.new('')
+            subtag2array(chr).each do |field|
+              hash[tag_get(field)] = truncate(tag_cut(field))
+            end
+            @data['CHROMOSOME'].push(hash)
+          end
+        end
+        @data['CHROMOSOME']
+      end
+
+      # PLASMID
+      def plasmids
+        unless @data['PLASMID']
+          @data['PLASMID'] = []
+          toptag2array(get('PLASMID')).each do |chr|
+            hash = Hash.new('')
+            subtag2array(chr).each do |field|
+              hash[tag_get(field)] = truncate(tag_cut(field))
+            end
+            @data['PLASMID'].push(hash)
+          end
+        end
+        @data['PLASMID']
+      end
+
+      # SCAFFOLD
+      def scaffolds
+        unless @data['SCAFFOLD']
+          @data['SCAFFOLD'] = []
+          toptag2array(get('SCAFFOLD')).each do |chr|
+            hash = Hash.new('')
+            subtag2array(chr).each do |field|
+              hash[tag_get(field)] = truncate(tag_cut(field))
+            end
+            @data['SCAFFOLD'].push(hash)
+          end
+        end
+        @data['SCAFFOLD']
+      end
+
+      # STATISTICS
+      def statistics
+        unless @data['STATISTICS']
+          hash = Hash.new(0.0)
+          get('STATISTICS').each_line do |line|
+            case line
+            when /nucleotides:\s+(\d+)/
+              hash['nalen'] = $1.to_i
+            when /protein genes:\s+(\d+)/
+              hash['num_gene'] = $1.to_i
+            when /RNA genes:\s+(\d+)/
+              hash['num_rna'] = $1.to_i
+            when /G\+C content:\s+(\d+.\d+)/
+              hash['gc'] = $1.to_f
+            end
+          end
+          @data['STATISTICS'] = hash
+        end
+        @data['STATISTICS']
+      end
+
+      def nalen
+        statistics['nalen']
+      end
+      alias length nalen
+
+      def num_gene
+        statistics['num_gene']
+      end
+
+      def num_rna
+        statistics['num_rna']
+      end
+
+      def gc
+        statistics['gc']
+      end
+
+      # GENOMEMAP
+      def genomemap
+        field_fetch('GENOMEMAP')
+      end
+
+    end
+    
+  end
+
+end
+
+
+
+if __FILE__ == $0
+
+  begin
+    require 'pp'
+    def p(arg); pp(arg); end
+  rescue LoadError
+  end
+
+  require 'bio/io/flatfile'
+
+  ff = Bio::FlatFile.new(Bio::KEGG::GENOME, ARGF)
+
+  ff.each do |genome|
+
+    puts "### Tags"
+    p genome.tags
+
+    [
+      %w( ENTRY entry_id ),
+      %w( NAME name ),
+      %w( DEFINITION definition ),
+      %w( TAXONOMY taxonomy taxid lineage ),
+      %w( REFERENCE references ),
+      %w( CHROMOSOME chromosomes ),
+      %w( PLASMID plasmids ),
+      %w( SCAFFOLD plasmids ),
+      %w( STATISTICS statistics nalen num_gene num_rna gc ),
+      %w( GENOMEMAP genomemap ),
+    ].each do |x|
+      puts "### " + x.shift
+      x.each do |m|
+        p genome.send(m)
+      end
+    end
+
+  end
+
+end
+
+
+=begin
+
+= Bio::KEGG::GENOME
+
+=== Initialize
+
+--- Bio::KEGG::GENOME.new(entry)
+
+=== ENTRY
+
+--- Bio::KEGG::GENOME#entry_id -> String
+
+      Returns contents of the ENTRY record as a String.
+
+=== NAME
+
+--- Bio::KEGG::GENOME#name -> String
+
+      Returns contents of the NAME record as a String.
+
+=== DEFINITION
+
+--- Bio::KEGG::GENOME#definition -> String
+
+      Returns contents of the DEFINITION record as a String.
+
+--- Bio::KEGG::GENOME#organism -> String
+
+      Alias for the 'definition' method.
+
+=== TAXONOMY
+
+--- Bio::KEGG::GENOME#taxonomy -> Hash
+
+      Returns contents of the TAXONOMY record as a Hash.
+
+--- Bio::KEGG::GENOME#taxid -> String
+
+      Returns NCBI taxonomy ID from the TAXONOMY record as a String.
+
+--- Bio::KEGG::GENOME#lineage -> String
+
+      Returns contents of the TAXONOMY/LINEAGE record as a String.
+
+=== COMMENT
+
+--- Bio::KEGG::GENOME#comment -> String
+
+      Returns contents of the COMMENT record as a String.
+
+=== REFERENCE
+
+--- Bio::GenBank#references -> Array
+
+      Returns contents of the REFERENCE records as an Array of Bio::Reference
+      objects.
+
+=== CHROMOSOME
+
+--- Bio::KEGG::GENOME#chromosomes -> Array
+
+      Returns contents of the CHROMOSOME records as an Array of Hash.
+
+=== PLASMID
+
+--- Bio::KEGG::GENOME#plasmids -> Array
+
+      Returns contents of the PLASMID records as an Array of Hash.
+
+=== SCAFFOLD
+
+--- Bio::KEGG::GENOME#scaffolds -> Array
+
+      Returns contents of the SCAFFOLD records as an Array of Hash.
+
+=== STATISTICS
+
+--- Bio::KEGG::GENOME#statistics -> Hash
+
+      Returns contents of the STATISTICS record as a Hash.
+
+--- Bio::KEGG::GENOME#nalen -> Fixnum
+
+      Returns number of nucleotides from the STATISTICS record as a Fixnum.
+
+--- Bio::KEGG::GENOME#num_gene -> Fixnum
+
+      Returns number of protein genes from the STATISTICS record as a Fixnum.
+
+--- Bio::KEGG::GENOME#num_rna -> Fixnum
+
+      Returns number of rna from the STATISTICS record as a Fixnum.
+
+--- Bio::KEGG::GENOME#gc -> Float
+
+      Returns G+C content from the STATISTICS record as a Float.
+
+=== GENOMEMAP
+
+--- Bio::KEGG::GENOME#genomemap -> String
+
+      Returns contents of the GENOMEMAP record as a String.
+
+== SEE ALSO
+
+  ftp://ftp.genome.jp/pub/kegg/genomes/genome
+
+=end